Nengo Loihi 0.6.0 released


The Nengo team at ABR is psyched to announce the release of Nengo Loihi 0.6.

What is Nengo Loihi?

Nengo Loihi is a backend for the Nengo neural simulator allowing standard spiking Nengo models to run on Intel’s new Loihi neuromorphic chip. Nengo Loihi includes an emulator so that you can develop spiking neuron models for Loihi without having access to hardware.

How do I use it?

Once installed, Nengo Loihi simulates Nengo networks. After defining your network, instead of simulating it with




and that’s it!

What’s new?

The most significant changes in this release relate to the syntax used for convolutional networks. The previous experimental syntax has been cleaned up and incorporated into the development version of Nengo core. Nengo Loihi 0.6.0 is now compatible with both the 2.8.0 release of Nengo and the development version. If you want to build convolutional networks, you will need the development version of Nengo core until a new version of Nengo core is released.

Several improvements were made to improve the accuracy of models trained with NengoDL, and to make more aspects of the model deterministic when seeded. If you find any situations in which a seeded model changes between runs, please file an issue on Github.

Finally, we have added dozens of tests in order to reach 100% coverage of the Nengo Loihi codebase and removed lots of unused or unnecessary code in the process. To see the full list of changes in Nengo Loihi 0.6.0, head to the Github release page.

How do I get it?

If you are using the emulator, then you can simply use pip.

pip install nengo-loihi

If you are setting up Nengo Loihi to use Loihi hardware for the first time, see the Nengo Loihi installation instructions.

Where can I learn more?

Where can I get help?

You’re already there! If you have any questions about Nengo Loihi, please ask in the Loihi category. And if you run in to any bugs or have suggestions for new features, file an issue through Github.